Health-aware hierarchical control for smart manufacturing using reinforcement learning

2017 ◽  
Author(s):  
Benjamin Y. Choo ◽  
Stephen Adams ◽  
Peter Beling
Keyword(s):  
Reinforcement Learning ◽  
Hierarchical Control ◽  
Smart Manufacturing

Action-inhibition hierarchies: Using a simple gastropod model to investigate serotonergic and dopaminergic control of action selection and reinforcement learning

2011 ◽  
Vol 26 (S2) ◽  
pp. 905-905
Author(s):  
S. Hodgkinson ◽  
J. Steyer ◽  
M. Jandl ◽  
W.P. Kaschka ◽  
Keyword(s):  
Animal Model ◽  
Reinforcement Learning ◽  
Hierarchical Control ◽  
Action Selection ◽  
Normal Function ◽  
Activity Level ◽  
Serotonergic Activity ◽  
General Activity Level ◽  
Planorbis Corneus ◽  
Conditioned Behaviour

IntroductionBasal ganglia (BG) activity plays an important role in action selection and reinforcement learning. Inputs from and to other areas of the brain are modulated by a number of neurotransmitter pathways in the BG. Disturbances in the normal function of the BG may play a role in the aetiology of psychiatric disorders such as schizophrenia and bipolar disorder.AimsDevelop a simple animal model to evaluate interactions between glutamatergic, dopaminergic, serotonergic and GABAergic neurones in the modulation of action selection and reinforcement learning.ObjectivesTo characterise the effects of changing dopaminergic and serotonergic activity on action selection and reinforcement learning in an animal model.MethodsThe food seeking / consummation (FSC) activity of the gastropod Planorbis corneus was suppressed by operant conditioning using a repeated unconditioned stimulus-punishment regime. The effects of elevated serotonin or dopamine levels (administration into cerebral, pedal and buccal ganglia), on operantly-conditioned FSC activity was assessed.ResultsOperantly-conditioned behaviour was reversed by elevated ganglia serotonin levels but snails showed no food consummation motor activity in the absence of food. In contrast, elevated ganglia dopamine levels in conditioned snails elicited food consummation motor movements in the absence of food but not orientation towards a food source.ConclusionsThe modulation of FSC activity elicited by reinforcement learning is subject to hierarchical control in gastropods. Serotoninergic activity is responsible establishing the general activity level whilst dopaminergic activity appears to play a more localised and subordinate ‘command’ role.

scholarly journals Self-repair of smart manufacturing systems by deep reinforcement learning

CIRP Annals ◽  
2020 ◽  
Vol 69 (1) ◽  
pp. 421-424 ◽  
Author(s):  
Bogdan I. Epureanu ◽  
Xingyu Li ◽  
Aydin Nassehi ◽  
Yoram Koren
Keyword(s):  
Reinforcement Learning ◽  
Manufacturing Systems ◽  
Smart Manufacturing ◽  
Self Repair ◽  
Smart Manufacturing Systems

scholarly journals Evaluation and Application of Urban Traffic Signal Optimizing Control Strategy Based on Reinforcement Learning

2018 ◽  
Vol 2018 ◽  
pp. 1-9
Author(s):  
Yizhe Wang ◽  
Xiaoguang Yang ◽  
Yangdong Liu ◽  
Hailun Liang
Keyword(s):  
Reinforcement Learning ◽  
Hierarchical Control ◽  
Traffic Signal ◽  
Urban Traffic ◽  
Learning Ability ◽  
Signal Control ◽  
Traffic Signal Control ◽  
Multidimensional Space ◽  
High Flows ◽  
Multiple Intersections

Reinforcement learning method has a self-learning ability in complex multidimensional space because it does not need accurate mathematical model and due to the low requirement for prior knowledge of the environment. The single intersection, arterial lines, and regional road network of a group of multiple intersections are taken as the research object on the paper. Based on the three key parameters of cycle, arterial coordination offset, and green split, a set of hierarchical control algorithms based on reinforcement learning is constructed to optimize and improve the current signal timing scheme. However, the traffic signal optimization strategy based on reinforcement learning is suitable for complex traffic environments (high flows and multiple intersections), and the effects of which are better than the current optimization methods in the conditions of high flows in single intersections, arteries, and regional multi-intersection. In a word, the problem of insufficient traffic signal control capability is studied, and the hierarchical control algorithm based on reinforcement learning is applied to traffic signal control, so as to provide new ideas and methods for traffic signal control theory.

scholarly journals Hierarchical control of multi-agent reinforcement learning team in real-time strategy (RTS) games

2021 ◽  
pp. 115707
Author(s):  
Weigui Jair Zhou ◽  
Budhitama Subagdja ◽  
Ah-Hwee Tan ◽  
Darren Wee-Sze Ong
Keyword(s):  
Reinforcement Learning ◽  
Real Time ◽  
Hierarchical Control ◽  
Multi Agent ◽  
Learning Team

scholarly journals Nigrostriatal Dopamine Signals Sequence-Specific Action-Outcome Prediction Errors

2021 ◽  
Author(s):  
Nick G. Hollon ◽  
Elora W. Williams ◽  
Christopher D. Howard ◽  
Hao Li ◽  
Tavish I. Traut ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Outcome Prediction ◽  
Hierarchical Control ◽  
Prediction Errors ◽  
Sequential Behavior ◽  
Nigrostriatal Dopamine ◽  
Health And Disease ◽  
Specific Prediction ◽  
Goal Directed Behavior ◽  
Self Stimulation

ABSTRACTDopamine has been suggested to encode cue-reward prediction errors during Pavlovian conditioning. While this theory has been widely applied to reinforcement learning concerning instrumental actions, whether dopamine represents action-outcome prediction errors and how it controls sequential behavior remain largely unknown. Here, by training mice to perform optogenetic intracranial self-stimulation, we examined how self-initiated goal-directed behavior influences nigrostriatal dopamine transmission during single as well as sequential instrumental actions. We found that dopamine release evoked by direct optogenetic stimulation was dramatically reduced when delivered as the consequence of the animal’s own action, relative to non-contingent passive stimulation. This action-induced dopamine suppression was specific to the reinforced action, temporally restricted to counteract the expected outcome, and exhibited sequence-selectivity consistent with hierarchical control of sequential behavior. Together these findings demonstrate that nigrostriatal dopamine signals sequence-specific prediction errors in action-outcome associations, with fundamental implications for reinforcement learning and instrumental behavior in health and disease.

scholarly journals Improvement of Refrigeration Efficiency by Combining Reinforcement Learning with a Coarse Model

Processes ◽  
2019 ◽  
Vol 7 (12) ◽  
pp. 967 ◽  
Author(s):  
Dapeng Zhang ◽  
Zhiwei Gao
Keyword(s):  
Reinforcement Learning ◽  
Conversion Efficiency ◽  
Hierarchical Control ◽  
Data Driven ◽  
Test Bed ◽  
Model Accuracy ◽  
Mechanism Model ◽  
Novel Approach ◽  
Coarse Model ◽  
Process Level

It is paramount to improve operational conversion efficiency in air-conditioning refrigeration. It is noticed that control efficiency for model-based methods highly relies on the accuracy of the mechanism model, and data-driven methods would face challenges using the limited collected data to identify the information beyond. In this study, a hybrid novel approach is presented, which is to integrate a data-driven method with a coarse model. Specifically, reinforcement learning is used to exploit/explore the conversion efficiency of the refrigeration, and a coarse model is utilized to evaluate the reward, by which the requirement of the model accuracy is reduced and the model information is better used. The proposed approach is implemented based on a hierarchical control strategy which is divided into a process level and a loop level. The simulation of a test bed shows the proposed approach can achieve better conversion efficiency of refrigeration than the conventional methods.

Sign in / Sign up

Export Citation Format

Share Document